Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/jscott3201/aionforge-memory/memory-handoffgit clone --depth 1 https://github.com/jscott3201/aionforge-memoryWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00015 | $0.00306 |
| Opus 5 | $0.00008 | $0.00153 |
| Sonnet 5 | $0.00003 | $0.00061 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
memory-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Aionforge Memory Handoff
Context: $ARGUMENTS
Create a handoff that future agents can use without replaying the whole session.
Procedure
- Check current evidence: branch, recent commits, PR number, CI state, changed files, validation commands, and remaining work.
- Search memory if prior handoffs, release state, or superseded decisions may matter.
- Capture focused records rather than one vague summary:
- Current status and what changed.
- Decisions made and why.
- Validation results and commands run.
- Known failures, blockers, or caveats.
- Exact next steps.
- Leave the remaining work as work items, not just prose:
work_create(orwork_advancean existing one) so the next agent canwork_querythe backlog instead of replaying the session. Tasks are work items, not memory episodes. - Use
supersedeswhen replacing an older handoff or corrected fact. - Report the new memory ids when audit, forget, restore, or supersession may matter.
Guardrails
- Do not capture secrets, credentials, private keys, raw tokens, or private log dumps.
- Mark uncertainty clearly; do not capture guesses as facts.
- User direction wins if they ask to avoid memory or limit what gets stored.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 31 lines · 15 tokens per session scan A 8f960c75d3c8
memory-handoff is a command published in the GitHub repository jscott3201/aionforge-memory (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 306 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
save-memory
You are saving what you learned this session into the megamemory knowledge graph. This is YOUR memory — record anything valuable for future sessions: what you understood about the project, what you built, decisions that were made, patterns you noticed, or intent the user shared.
bootstrap-memory
RUN { git ls-files; git ls-files --others --exclude-standard; } 2>/dev/null | sort -u | xargs wc -l 2>/dev/null | sort -rn | head -150 READ README.md.
tm-save
Save this session's durable memory to trailmem before you exit.
rp-build-cli
Build with rp-cli context builder → chat → implement.
export
Export a knowledge abstract to an Obsidian vault — a folder of Markdown notes linked by [[wikilinks]].
spec-orchestrator
Orchestrate implementation of a large specification using parallel agent teams. Reads specs via discovery subagents, synthesizes a task plan, spawns implementation teammates, and manages wave-based execution.